Stanford Seminar - Objects, Skills, and the Quest for Compositional Robot Autonomy

This course focuses on the quest for compositional robot autonomy by integrating scientific advances in AI with engineering disciplines. The learning outcomes include understanding the role of abstraction and composition in building robot autonomy, developing actionable object representations, and scaffolding long-horizon tasks with sensorimotor skills. The course teaches skills such as neural task programming, robotic grasping, and characterizing objects. The teaching method involves lectures on topics like the compositional robot autonomy stack, neural fields, and supervised procedures. The intended audience for this course includes robotics enthusiasts, AI engineers, and individuals interested in the intersection of AI and robotics.